Moorfields Eye Hospital launches first virtual assistant to connect with patients IBM BLog

Moorfields Eye Hospital launches first virtual assistant to connect with patients

Moorfields Eye Hospital NHS Foundation Trust has launched a new virtual assistant, specially designed to engage with patients and the public.

The Oriel Assistant will provide answers to questions from patients, staff and the general public.

Turning the traditional virtual assistant model on its head, this new healthcare technology will use its understanding of natural language to ask relevant questions whenever it recognises a particular theme.

This will lead to a two-way question and answer conversation between the person and the virtual assistant.

You can read more about how the Oriel Assistant and AI healthcare technology is transforming Moorfields’ healthcare in the following articles.


How technology improves healthcare

Moorfields Eye Hospital launches first virtual assistant to connect with patients
Moorfields Eye Hospital NHS Foundation 

The Oriel Assistant is the first product of the Maia (Moorfields AI Assistant) Project. After the initial roll out, Moorfields plan to expand the capabilities of its AI-powered assistants, training them to respond to day-to-day queries patients have about the hospital, their appointments, and their care, while continuing to make it more and more accessible to those with reduced vision.

Peter Thomas, Director of Digital Innovation and Consultant Paediatric Ophthalmologist at Moorfields, said: “Moorfields has established a reputation as an early leader in researching the clinical applications of artificial intelligence. The release of Oriel Assistant is an important milestone as we are making an AI-powered service available to the public, and also helping to avoid the digital exclusion of visually impaired users. As we move forward with the Maia project, we plan to expand its capabilities to communicate with patients when they most need it, or are most worried about their vision – even if that is in the middle of the night. Importantly, we plan to make our AI assistants available via voice, so that patients with any level of vision can benefit from this technology.”


New technologies enhancing healthcare technology

Moorfields Eye Hospital launches chatbot to cope with strained resources         
Computerworld, Tom Macaulay Senior Online Editor

The NHS faces mounting financial pressures from an aging population, rising treatment costs, and slowing increases in government funding. Moorfields Eye Hospital believes a new chatbot will help it fill the gap.

Peter Thomas, director of digital innovation and a consultant paediatric ophthalmologist at Moorfields, told Computerworld UK that the Oriel relocation provides the perfect test for the chatbot before it’s expanded to queries about conditions and treatments.

“We’d start with things like interactive patient information leaflets,” he said. “We have a system where when you receive a diagnosis, we give you a patient information leaflet, and you want to know one thing, but you have to read through five or six pages of information to get to it. It would be nice if patients could go to a chatbot, and just ask a general question about their condition.”

Thomas believes the chatbot will prove extremely useful for NHS service users, who currently often struggle to navigate the health service’s complex array of communication channels.

Moorfields investigated how this applied to the experience of its own patients by analysing the content of phone calls to the various hospital departments. They found that numerous calls requested computable data on subjects such as appointment times and contact information, which a chatbot could respond to with greater speed and efficiency than a human.


Healthcare technology 

Moorfields chatbot to field questions on new £344m eye care facility
Digital Health, Owen Hughes

Moorfields Eye Hospital has introduced a chatbot-style virtual assistant to provide information on the proposal and gather feedback…Oriel Assistant is able to answer questions and allows patients, staff and the general public to have their say on the plans.

Answers gathered by the assistant will be fed into a broader consultation, which closes on 16 September 2019.

David Probert, chief executive for Moorfields Eye Hospital, said: “This is an exciting step forward towards delivering the modern, efficient and effective care our patients deserve.

“Central to this is our proposal to move our hospital to a new purpose-built centre where we would be able to transform lives, turn research into new treatments faster and share our knowledge and understanding with the clinicians of tomorrow.

“But innovation is not just limited to our clinical environment; it is also about how we connect with our patients. That is why we have developed the Oriel Assistant, to provide round-the-clock answers to questions and information about how the proposal could affect our patients, staff and the wider public.”

Hosted on the…Cloud, users can interact directly with the chatbot via a dedicated landing page on the Oriel website.

Beyond its initial use, Moorfields plans to explore how chatbots and AI-based technology can be used to support patients elsewhere.


How has technology changed the healthcare industry?

Now DeepMind’s AI can spot eye disease just as well as your doctor
Wired, Matt Burgess

An automated algorithm to diagnose eye diseases from Moorfields’ and Google’s London-based artificial intelligence unit, DeepMind, may have the potential to cut down the amount of time doctors spend diagnosing from OCT scans. New research published in the journal Nature Medicine shows DeepMind’s AI being taught to recognise 50 common eye problems – including three of the biggest eye diseases: glaucoma, diabetic retinopathy and age-related macular degeneration.

The researchers used two neural networks – algorithms modelled on the brain – to understand the OCT scans and determine what may be wrong with the eye. Both networks were trained, using deep learning, on existing scans. The first neural network was trained to spot different features of diseases in OCT scans. A team of ten expert ophthalmologists and optometrists spent hours highlighting diseases on scans which were then fed to the neural network to learn from, Keane says. In total, the AI system was trained on 14,884 scans – even though DeepMind had access to one million OCT images.

The second neural network analysed the output of the first and is able to present doctors with diagnoses and a referral recommendation. The systems give a confidence rating in the form of a percentage. “It doesn’t just say this looks like a macular degeneration, the algorithm says here are the specific aspects of the scan which we think indicate the diagnosis. It marks up the scan itself,” Suleyman says.


Back to top